Cardiac Autonomic Regulation Activity in Bhang-Consuming Indian Male Volunteers: Statistical Analysis and A Comparative Study of Machine Learning Models

Abstract

The consumption of cannabis-based products is increasing worldwide day by day because of their euphoric effects. Numerous studies have reported the incidence of cardiovascular diseases and even mortality in people consuming cannabis. However, little attention has been paid to understanding the cannabis-induced alteration in the Cardiac Autonomic Regulation (CAR) activity, which can help in the early diagnosis of cardiovascular diseases. The current study investigated the alteration in the CAR activity of 200 Indian male volunteers due to the consumption of bhang (a cannabis-based product) using various analyses on heart rate variability (HRV) signals. The results suggested a reduction in the heart rate variability, increased sympathetic dominance, and a corresponding decrease in parasympathetic activity in the bhang-consuming population, which may lead to various cardiovascular diseases. These inferences can act as evidence for counseling people to stop consuming cannabis. Additionally, this study developed and compared different machine learning (ML) models for classifying cannabis consumers and non-consumers using their HRV data. Based on the comparison of the performance indices, the Gradient Boosted Tree (GBT) model derived from discrete wavelet transform (DWT) coefficients using Ginni Index-based feature selection was proposed as the best ML classifier among the ML models developed in this study.